Predicting of the refractive index of haemoglobin using the Hybrid GA-SVR approach

Tajudeen A Oyehan; Ibrahim O Alade; Aliyu Bagudu; Kazeem O Sulaiman; Sunday O Olatunji; Tawfik A Saleh

doi:10.1016/j.compbiomed.2018.04.024

Predicting of the refractive index of haemoglobin using the Hybrid GA-SVR approach

Comput Biol Med. 2018 Jul 1:98:85-92. doi: 10.1016/j.compbiomed.2018.04.024. Epub 2018 Apr 30.

Authors

Tajudeen A Oyehan¹, Ibrahim O Alade², Aliyu Bagudu³, Kazeem O Sulaiman⁴, Sunday O Olatunji⁵, Tawfik A Saleh⁶

Affiliations

¹ Geosciences Department, College of Petroleum Engineering & Geosciences, King Fahd University of Petroleum & Minerals (KFUPM), Dhahran, 31261, Saudi Arabia.
² Department of Physics, Faculty of Science, Universiti Putra Malaysia, UPM, 43400, Serdang, Malaysia; College of Industrial Management King Fahd University of Petroleum & Minerals (KFUPM), Dhahran, 31261, Saudi Arabia.
³ Information and Computer Science Department, College of Computer Science and Engineering, King Fahd University of Petroleum & Minerals (KFUPM), Dhahran, 31261, Saudi Arabia.
⁴ Department of Chemistry, University of Saskatchewan, 110 Science Place, Saskatoon, SK S7N 5C9, Canada.
⁵ Department of Computer Science, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia.
⁶ Department of Chemistry, King Fahd University of Petroleum and Mineral, Dhahran, 31261, Saudi Arabia. Electronic address: tawfik@kfupm.edu.sa.

PMID: 29777986
DOI: 10.1016/j.compbiomed.2018.04.024

Abstract

The optical properties of blood play crucial roles in medical diagnostics and treatment, and in the design of new medical devices. Haemoglobin is a vital constituent of the blood whose optical properties affect all of the optical properties of human blood. The refractive index of haemoglobin has been reported to strongly depend on its concentration which is a function of the physiology of biological cells. This makes the refractive index of haemoglobin an essential non-invasive bio-marker of diseases. Unfortunately, the complexity of blood tissue makes it challenging to experimentally measure the refractive index of haemoglobin. While a few studies have reported on the refractive index of haemoglobin, there is no solid consensus with the data obtained due to different measuring instruments and the conditions of the experiments. Moreover, obtaining the refractive index via an experimental approach is quite laborious. In this work, an accurate, fast and relatively convenient strategy to estimate the refractive index of haemoglobin is reported. Thus, the GA-SVR model is presented for the prediction of the refractive index of haemoglobin using wavelength, temperature, and the concentration of haemoglobin as descriptors. The model developed is characterised by an excellent accuracy and very low error estimates. The correlation coefficients obtained in these studies are 99.94% and 99.91% for the training and testing results, respectively. In addition, the result shows an almost perfect match with the experimental data and also demonstrates significant improvement over a recent mathematical model available in the literature. The GA-SVR model predictions also give insights into the influence of concentration, wavelength, and temperature on the RI measurement values. The model outcome can be used not only to accurately estimate the refractive index of haemoglobin but also could provide a reliable common ground to benchmark the experimental refractive index results.

Keywords: Genetic algorithm; Haemoglobin; Refractive index; Support vector regression.

MeSH terms

Algorithms
Databases, Factual
Hemoglobins / analysis*
Humans
Models, Biological
Refractometry / methods*
Regression Analysis
Support Vector Machine*

Substances

Hemoglobins